The DOI matches its Crossref record; 140 of the 168 references it cites were found in a registry or an index; 10 of the 54 sources its claims cite were checked for support.
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Open accessAbstract
With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 of 54 cited sources checked · 4 supported · 0 flagged · accuracy not yet measured
Every source the paper cites for this claim was checked and supports it.
In the paper
“Stamoulis et al. [106] cast the adaptive DNN model selection issue as a hyperparameter optimization problem by taking into account the accuracy and communication constraints imposed by the devices.Then, a Bayesian optimization (BO) is adopted to solve this problem, achieving an improvement by up to 6× in terms of minimum energy per image under accuracy constraints.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Park et al.
What the sources say
- Supportedcites [106] 106. D. Stamoulis et al., "Designing adaptive neural networks for energy-constrained image classification," in Proc. ACM ICCAD, 2018, Art. no. 23. source
Section 4.1 (p. 4) formulates adaptive CNN design, including network selection, as a hyperparameter optimization problem. Section 4.2 (p. 4) says the authors adapt Bayesian optimization to solve it, and the Conclusion (p. 8) reports up to 6× lower minimum energy per image under accuracy constraints than previously published methods. (LLM, conf=0.94)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The result varies with architectures and transfer techniques.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [62] 62. R. Sharma, S. Biookaghazadeh, B. Li, and M. Zhao, "Are existing knowledge transfer techniques effective for deep learning with edge devices?" in Proc. IEEE Int. Conf. Edge Comput. (EDGE), Jul. 2018, pp. 42-49. source
- Could not verifycites [44] 44. Q. Chen, Z. Zheng, C. Hu, D. Wang, and F. Liu, "Data-driven task allocation for multi-task transfer learning on the edge," in Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019. sourceExperimental — accuracy not yet measured
Section 5.2.2 (p. 6) reports accuracy for one architecture under different distributed-training conditions, but does not compare architectures or transfer-learning techniques. Section 6 (p. 6) calls studies of other DNN architectures future work. Searches for transfer learning and variation across architectures or transfer techniques found no passage addressing the claim. (LLM, conf=0.76)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Cachier can increase responsiveness by 3× or more.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Could not verifycites [93] 93. U. Drolia, K. Guo, J. Tan, R. Gandhi, and P. Narasimhan, "Cachier: Edge-caching for recognition applications," in Proc. IEEE ICDCS, Jun. 2017, pp. 276-286. sourceExperimental — accuracy not yet measured
The Results section discusses Edgent’s inference latency, but does not report a result for Cachier. Searches for “Cachier” and “responsiveness three times” found no passage supporting a 3× improvement. (LLM, conf=0.77)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Data Generated at the Network Edge Need AI to Fully Unlock Their Potential”
- Also stated in: § A. Motivation and Benefits of Edge Intelligence · boosted
“AI will be functionally necessary due to its ability to quickly analyze those huge data volumes and extract insights from them for high-quality decision making.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > A. Motivation and Benefits of Edge Intelligence
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § A. Motivation and Benefits of Edge Intelligence · boosted
In the paper
“Cisco estimates that nearly 850 ZB will be generated by all people, machines, and things at the network edge by 2021 [3].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not matchedcites [3] 3. Cisco Global Cloud Index: Forecast and Methodology, 2016-2021, White Paper. [Online]. Available: https://www.cisco.com/c/en/us/ solutions/collateral/service-provider/global- cloud-index-gci/white-paper-c11-738085.html
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
In the paper
“Lin et al. [53] observe that 99.9% of the gradient exchange in distributed SGD (DSGD) are redundant, which demonstrates the power of gradient compression.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 3) Gradient Compression:
What the sources say
- Not checked — no full text of the sourcecites [53] 53. Y. Lin, S. Han, H. Mao, Y. Wang, and W. J. Dally, "Deep gradient compression: Reducing the communication bandwidth for distributed training," 2017, arXiv:1712.01887. [Online]. Available: https://arxiv.org/abs/1712.01887 source
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“Specifically, while preserving client's own privacy, the training loss can be reduced by sharing the models among clients, comparing to training solely on their own inputs.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Not checked — no full text of the sourcecites [46] 46. R. Shokri and V. Shmatikov, "Privacy-preserving deep learning," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1310-1321. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios”
- Also stated in: § 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios: · hedged
“edge computing is proposed to achieve low-latency data processing by sinking the computing capability from the cloud data center to the edge side, i.e., data generation source, which may enable AI processing with high performance.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios: · hedged
In the paper
“A flaw of [46] is that it does not consider unbalanced and nonindependent identical distribution (non-IID) data.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Not checked — no full text of the sourcecites [46] 46. R. Shokri and V. Shmatikov, "Privacy-preserving deep learning," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1310-1321. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIn the paper
“big data have recently gone through a radical shift of data source from the megascale cloud datacenters to the increasingly widespread end devices, e.g., mobile devices and Internetof-Things (IoT) devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not matchedcites [3] 3. Cisco Global Cloud Index: Forecast and Methodology, 2016-2021, White Paper. [Online]. Available: https://www.cisco.com/c/en/us/ solutions/collateral/service-provider/global- cloud-index-gci/white-paper-c11-738085.html
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Not matched
- Probably not a substantial claim. 28
- It may state two separate claims as one. 27
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“VGG-16 [19] is trained to a deeper structure of 16 layers consisting of 13 convolution layers and three fully connected layers, requiring 138 million weights and 15.5G MACs to classify the image with a size of 224 × 224.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Partly supportedcites [19] 19. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," 2014, arXiv:1409.1556. [Online]. Available: https://arxiv.org/abs/1409.1556 sourceExperimental — accuracy not yet measured
Table 1 (p. 3) identifies configuration D as a 16-weight-layer network with a 224 × 224 RGB input, and Table 2 (p. 3) lists 138 million parameters for D. Section 2.1 (p. 2) describes the three fully connected layers. Our copy does not report the claimed 15.5G MACs per image, so that part is unsupported. (LLM, conf=0.88)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In particular, an update aggregation protocol named FedCS is developed to allow the centralized server to aggregate as many client updates as possible and to accelerate performance improvement in ML models.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Could not verifycites [52] 52. T. Nishio and R. Yonetani, "Client selection for federated learning with heterogeneous resources in mobile edge," 2018, arXiv:1804.08333. [Online]. Available: https://arxiv.org/abs/ 1804.08333 sourceExperimental — accuracy not yet measured
The Introduction (p. 2) describes pruning, quantization, and Huffman coding, while §6.3 (pp. 9–10) discusses inference speedups from compression. Searches for FedCS, client-update aggregation, and federated client selection found no passage addressing the claimed protocol or its effect on model improvement. (LLM, conf=0.76)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Could not verify
Every source the paper cites for this claim was checked and supports it.
In the paper
“The optimization in [45] emphasizes the properties of unbalanced and non-IID since the distributed data may come from various sources.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Supportedcites [45] 45. H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas, "Communication-efficient learning of deep networks from decentralized data," 2016, arXiv:1602.05629. [Online]. Available: https://arxiv.org/abs/1602.05629 source
The Introduction (p. 2) explicitly says the work emphasizes the non-IID and unbalanced properties of federated optimization. It explains that clients’ data reflect different users’ device usage and that users contribute varying amounts of data, supporting the citing sentence’s explanation of why those properties arise. (LLM, conf=0.94)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“when moving a tremendous amount of data across the wide area network (WAN), both monetary cost and transmission delay can be prohibitively high, and the privacy leakage can also be a major concern [5].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Could not verifycites [5] 5. Q. Pu et al., "Low latency geo-distributed data analytics," in Proc. ACM SIGCOMM, 2015, pp. 421-434. sourceExperimental — accuracy not yet measured
The Introduction and Section 6 (Advantages and disadvantages; page numbers unavailable) discuss generative models and their computational properties, not transferring large datasets over a WAN. Searches for WAN costs, transmission delay, and privacy leakage found no passage addressing the claim. (LLM, conf=0.75)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“the physical proximity between the computing and information-generation sources promises several benefits compared to the traditional cloud-based computing paradigm, including low latency, energy efficiency, privacy protection, reduced bandwidth consumption, on-premises, and context awareness [6], [8].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not checked — no full text of the sourcecites [6] 6. W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE Internet Things J., vol. 3, no. 5, pp. 637-646, Oct. 2016. source
- Supportedcites [8] 8. Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, "A survey on mobile edge computing: The communication perspective," IEEE Commun. Surveys Tuts., vol. 19, no. 4, pp. 2322-2358, 4th Quart., 2017. source
The comparison in “Mobile Edge Computing Versus Mobile Cloud Computing” (p. 3) identifies lower latency, mobile-device energy savings, context awareness, and improved privacy and security as MEC advantages. “Mobile Computing for 5G: From Clouds to Edges” (p. 1) explains that moving traffic toward the edge avoids burdening backhaul networks, while the privacy discussion (p. 3) gives enterprise-managed deployment as an example of keeping data on premises. (LLM, conf=0.88)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“A good performance improvement is obtained by transferring knowledge from both the intermediate layers and last layer of the teacher to a shallower student while other architectures and transfer techniques do not fare so well and some of them even lead to negative performance impact.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [62] 62. R. Sharma, S. Biookaghazadeh, B. Li, and M. Zhao, "Are existing knowledge transfer techniques effective for deep learning with edge devices?" in Proc. IEEE Int. Conf. Edge Comput. (EDGE), Jul. 2018, pp. 42-49. source
- Could not verifycites [44] 44. Q. Chen, Z. Zheng, C. Hu, D. Wang, and F. Liu, "Data-driven task allocation for multi-task transfer learning on the edge," in Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019. sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
Every source the paper cites for this claim was checked and supports it.
In the paper
“The early work on random gossip algorithms is gossip averaging [63], which can fast converge toward a consensus among nodes by exchanging information peer to peer.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Supportedcites [63] 63. S. Boyd, A. Ghosh, B. Prabhakar, and D. Shah, "Randomized gossip algorithms," IEEE Trans. Inf. Theory, vol. 52, no. 6, pp. 2508-2530, Jun. 2006. source
The paper describes gossip averaging as nodes communicating with randomly chosen neighbors (Randomized Gossip Algorithms, p. 1). It studies convergence to the vector of averages and the design of the fastest gossip algorithm (Previous Results, p. 3; Randomized Gossip Algorithms, p. 1), supporting the peer-to-peer consensus paraphrase. (LLM, conf=0.89)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
In the paper
“The algorithm is based on the convergence analysis of distributed gradient descent and can be applied to federated learning in edge computing with provable convergence.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Not matchedcites [51] 51. S. Wang et al., "Adaptive federated learning in resource constrained edge computing systems," IEEE J. Sel. Areas Commun., vol. 37, no. 3, pp. 1205-1221, Jun. 2019.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result, the transmission latency of data offloading decreases, the data privacy increases, and the WAN bandwidth cost reduces.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The main challenges of federated learning are optimization and communication.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While edge computing and AI complement each other from a technical perspective, their application and popularization are also mutually beneficial.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Though the federated learning technique exploits a new decentralized deep learning architecture, it is built upon a central server for aggregating local updates.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“As forecast by Gartner [33], more than 80% of enterprise IoT projects will include an AI component by 2022, up from only 10% today.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > A. Motivation and Benefits of Edge Intelligence
What the sources say
- Not matchedcites [33] 33. AI Trends for Enterprise Computing. [Online]. Available: https://www.gartner.com/ smarterwithgartner/3-ai-trends-for-enterprise- computing/
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This conflict indicates that there is no”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Load-bearingStrength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Energy efficiency is mainly affected by the size of the target training model and resources of the used devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 6) Energy Efficiency:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“ResNet [20], the state-of-the-art effort, uses the”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not checked — no full text of the sourcecites [20] 20. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE CVPR, Jun. 2016, pp. 770-778. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“real-time video analytics is envisioned to be a killer application for edge computing [12], [37], [38].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Computing Can Be Popularized With AI Applications:
What the sources say
- Not checked — no full text of the sourcecites [12] 12. G. Ananthanarayanan et al., "Real-time video analytics: The killer app for edge computing," Computer, vol. 50, no. 10, pp. 58-67, 2017. source
- Not checked — no full text of the sourcecites [37] 37. H. Zhang, G. Ananthanarayanan, P. Bodik, M. Philipose, P. Bahl, and M. J. Freedman, "Live video analytics at scale with approximation and delay-tolerance," in Proc. USENIX NSDI, 2017, pp. 377-392.
- Not checked — no full text of the sourcecites [38] 38. C.-C. Hung et al., "VideoEdge: Processing camera streams using hierarchical clusters," in Proc. IEEE/ACM Symp. Edge Comput. (SEC), Oct. 2018, pp. 115-131. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“AlexNet requires 61 million weights and 724 million MACs (multiply-add computation) to classify the image with a size of 227 × 227.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not matchedcites [18] 18. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Proc. NIPS, 2012, pp. 1097-1105.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“However, Gaia focuses on geodistributed datacenters that are capacity-unlimited, making it is not generally applicable to edge computing nodes whose capacity is highly constrained.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Not matchedcites [50] 50. K. Hsieh, A. Harlap, N. Vijaykumar, D. Konomis, G. R. Ganger, and P. B. Gibbons, "Gaia: Geo-distributed machine learning approaching LAN speeds," in Proc. NSDI, 2017, pp. 629-647.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Under the decentralized training mode, the convergence value depends on the way the gradient is synchronized and updated.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Convergence:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When training the DNN model by using the data originated at a massive of end devices, the raw data or intermediate data should be transferred out of the end devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 3) Privacy:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep learning represents the state-of-the-art AI technology as well as a highly resource-demanding workload that naturally suits for edge computing.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > B. Deep Learning and Deep Neural Networks
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When training the DNN model in a decentralized manner, both the computation and communication processes consume enormous energy.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 6) Energy Efficiency:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
- Rests on an assumption: For most end devices, they are energy-constrained.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, this is achieved at the cost of increased computational latency and energy consumption.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not checked — no full text of the sourcecites [28] 28. C. Szegedy et al., "Going deeper with convolutions," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 1-9. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“MeDNN improves the DNN model inference by 1.86-2.44×with two to four worker nodes and saves 26.5% of additional computing time and 14.2% of extra communication time.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [84] 84. J. Mao et al., "MeDNN: A distributed mobile system with enhanced partition and deployment for large-scale DNNs," in Proc. 36th Int. Conf. Comput.-Aided Design, Nov. 2017, pp. 751-756. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Communication overhead is affected by the size of the original input data, the way of transmission, and the available bandwidth.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Due to the combinatorial nature, the high-dimensional configuration problem involves a huge search space of parameters and is very challenging to tackle.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > D. Summary of Existing Systems and Frameworks
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, data parallelism may bring heavy overhead of communication, while model parallelism usually leads to severe underutilization of computation resources.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
In the paper
“PipeDream shows the advantage of reducing communication overhead and utilizing computing resource efficiently.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [61] 61. A. Harlap, D. Narayanan, A. Phanishayee, V. Seshadri, G. R. Ganger, and P. B. Gibbons, "PipeDream: Fast and efficient pipeline parallel DNN training," 2018, arXiv:1806.03377. [Online]. Available: https://arxiv.org/abs/1806.03377 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The communication latency may vary from the size of transmitted raw or intermediate data and the bandwidth of network connection.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“By deployment on large-scale systems, Daily et al. [66] show that the trivial gossip-based algorithms at scale lead to a communication imbalance, poor convergence, and heavy communication overhead.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [66] 66. J. Daily, A. Vishnu, C. Siegel, T. Warfel, and V. Amatya, "GossipGraD: Scalable deep learning using gossip communication based asynchronous gradient descent," 2018, arXiv:1803.05880. [Online]. Available: https://arxiv.org/ abs/1803.05880 source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“FoggyCache reduces computation latency and energy consumption by a factor of 3× to 10×.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Not checked — no full text of the sourcecites [95] 95. P. Guo, B. Hu, R. Li, and W. Hu, "FoggyCache: Cross-device approximate computation reuse," in Proc. ACM Mobicom, 2018, pp. 19-34. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Arguably, latency is one of the most fundamental performance indicators of distributed DNN model training since it directly influences when the trained model is available for use.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is based on the important observation that a DNN model can be split inside between two successive layers with two partitions deployed on different locations without losing accuracy.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the proposed automatic optimization framework AdaDeep [75] systematically formulates the goals and constraints on accuracy, latency, storage, and energy into a unified optimization problem and leverages DRL to effectively find a good combination of compression techniques.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [75] 75. S. Liu, Y. Lin, Z. Zhou, K. Nan, H. Liu, and J. Du, "On-demand deep model compression for mobile devices: A usage-driven model selection framework," in Proc. 16th Annu. Int. Conf. Mobile Syst., Appl., Services, 2018, pp. 389-400. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The decentralized architecture is naturally friendly to user's privacy, for which the systems that are based on the decentralized architecture such as BlockFL and GossipGraD typically preserve privacy better.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Table 2 Overview of Systems and Frameworks on EI Model Training
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Intuitively, this communication overhead increases the training latency, energy, and bandwidth consumption.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Precog uses predictions of Markov chains to prefetch data onto the mobile device and reach a speedup of 5×.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Not checked — no full text of the sourcecites [94] 94. U. Drolia, K. Guo, and P . Narasimhan, "Precog: Prefetching for image recognition applications at the edge," in Proc. ACM/IEEE Symp. Edge Comput. (SEC), Oct. 2017, p. 17. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared with the DNN training under the cloud-based framework, the DNN training under edge-based framework pays more attention to protecting users' privacy and training an available deep learning model faster.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Table 2 Overview of Systems and Frameworks on EI Model Training
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The latency of the distributed training process typically consists of the computation latency and the communication latency.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Both Blot et al. [64] and Jin et al. [65] apply gossip algorithms on the updates of SGD, but neither of them has performance convergence degradation at large scale.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [64] 64. M. Blot, D. Picard, M. Cord, and N. Thome, "Gossip training for deep learning," 2016, arXiv:1611.09726. [Online]. Available: https://arxiv.org/abs/1611.09726 source
- Not checked — no full text of the sourcecites [65] 65. P. H. Jin, Q. Yuan, F. Iandola, and K. Keutzer, "How to scale distributed deep learning?" 2016, arXiv:1611.04581. [Online]. Available: https://arxiv.org/abs/1611.04581 source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“ReXCam reduces computation workload by 4.6× and improves DNN model inference accuracy by 27%.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Input Filtering:
What the sources say
- Not checked — no full text of the sourcecites [99] 99. S. Jain, J. Jiang, Y. Shu, G. Ananthanarayanan, and J. Gonzalez, "ReXCam: Resource-efficient, cross-camera video analytics at enterprise scale," 2018, arXiv:1811.01268. [Online]. Available: https://arxiv.org/abs/1811.01268 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“For the object recognition application, Huang et al. [120] investigate the influence of the main factors, e.g., number of proposals, input image size, and the selection of feature extractor, on inference speed and accuracy.Based on their experiment results, a new combination of these factors is found to outperform the state-of-the-art method.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > D. Tradeoff Design With Various DNN Performance Metrics
What the sources say
- Not checked — no full text of the sourcecites [120] 120. J. Huang et al., "Speed/accuracy trade-offs for modern convolutional object detectors," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 7310-7311. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
In the paper
“Compared to the approach that uploads the entire model, IONN significantly improves query performance and energy consumption during DNN model uploading.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [82] 82. H.-J. Jeong, H.-J. Lee, C. H. Shin, and S.-M. Moon, "IONN: Incremental offloading of neural network computations from mobile devices to edge servers," in Proc. ACM Symp. Cloud Comput., 2018, pp. 401-411. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The gossip distributed algorithms enjoy the advantage of full asynchronization and total decentralization as they have no requirement on centralized nodes or variables.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“the cascading network [91] simply adds the MP layer and fully connected layer to the standard DNN model and achieves a speedup of 20%.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > The aggregation methods work when multiple mobile
What the sources say
- Not checked — no full text of the sourcecites [91] 91. S. Leroux et al., "The cascading neural network: Building the Internet of smart things," Knowl. Inf. Syst., vol. 52, no. 3, pp. 791-814, 2017.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This process will tend to work if the features are general (i.e., suitable to both base and target tasks) instead of specific to the base task.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper relies on this without support.
There is a lack of a dedicated venue for summarizing, discussing, and disseminating recent advances of edge intelligence in both industry and academia.
“There is, in general, a lack of venue dedicated for summarizing, discussing, and disseminating the recent advances of EI, in both industrial and academia.”
The paper relies on this without support.
Research and practice on edge intelligence are still in a very early stage.
“Notably, research and practice on this emerging interdiscipline-EI-are still in a very early stage.”
The paper relies on this without support.
The edge ecosystem will present many novel application scenarios for AI and fuel the continuous booming of AI.
“Clearly, via bringing the huge volumes of data to AI, the edge ecosystem will present many novel application scenarios for AI and fuel the continuous booming of AI.”
The paper relies on this without support.
For most end devices, they are energy-constrained.
“However, for most end devices, they are energy-constrained.”
The paper relies on this without support.
It is inevitable to deal with privacy issues when raw or intermediate data are transferred out of end devices.
“Obviously, it is inevitable to deal with privacy issues in this scenario.”
The paper relies on this without support.
For some real-time intelligent mobile applications, they usually have stringent deadline requirement such as 100-ms latency.
“For some real-time intelligent mobile applications (e.g., AR/VR mobile gaming and intelligent robots), they usually have stringent deadline requirement such as 100-ms latency.”
The paper relies on this without support.
For some mobile applications requiring high reliability, they demand ultrahigh accuracy on DNN model inference.
“For some mobile applications requiring a high level of reliability, such as self-driving car and face authentication, they demand the ultrahigh accuracy on the DNN model inference.”
The paper relies on this without support.
Most existing efforts use a single compression technique.
“While most existing efforts use a single compression technique, they may not suffice to meet the diverse requirements and constraints on accuracy, latency, storage, and energy imposed by some IoT devices.”
The paper relies on this without support.
Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
“However, it is difficult for software developers to choose an appropriate DNN model for the EI application because the standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.”
The paper relies on this without support.
Most current edge AI programming/software platforms mainly serve as relays for connecting to cloud data centers.
“Nevertheless, currently, most of these platforms mainly serve as relays for connecting to the powerful cloud data centers.”
The paper relies on this without support.
Most deep learning-based AI models are highly resource-intensive.
“Most of the deep learning-based AI models are highly resourceintensive, which means that powerful computing capability supported by abundant hardware resources (e.g., GPU, field-programmable gate array (FPGA), and TPU) is important to boost the performance of these AI models.”
The paper relies on this without support.
For an EI application with a specific mission, there is usually a series of DNN model candidates that are capable of finishing the task.
“For an EI application with a specific mission, there is usually a series of DNN model candidates that are capable of finishing the task.”
The paper relies on this without support.
The service environments for many EI application scenarios are of high dynamics and it is hard to accurately predict future events.
“Since for many EI application scenarios (e.g., smart cities), the service environments are of high dynamics and it is hard to accurately predict future events.”
The paper relies on this without support.
The high-efficiency operation of EI services may require close collaboration and integration across different service providers.
“The high-efficiency operation of EI services may require close collaboration and integration across different service providers, e.g., for implementing expanded resource sharing and smooth service handover.”
The paper relies on this without support.
A user can be a service consumer and, meanwhile, a data generator as well.
“Also, for EI service, a user can be a service consumer and, meanwhile, a data generator as well.”
The paper relies on this without support.
There is a stringent need to push the AI frontier from the cloud to the network edge.
“Driving by flourishing of both AI and IoT, there is a stringent need to pushing the AI frontier from the cloud to the network edge.”
The paper relies on this without support.
Edge computing is widely recognized as a promising solution to support computation-intensive AI applications in resource-constrained environments.
“To fulfill this trend, edge computing has been widely recognized as a promising solution to support computation-intensive AI applications in resource-constrained environments.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Additionally, UAVs generate lots of data at the network edge and directly sharing original data sets between many edge nodes has a high risk associated with it [8].”
From A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Edge Intelligence (EI) Zhou et al. (2019) proposes a new paradigm combining AI and edge computing, with the goal of performing distributed computing of DL models.”
From Deepfakes: current and future trends (2024) · cites this paper as Zhou et al. 2019
The cited source says what the claim attributes to it.
In the citing paper
“This entails some advantages such as low latency, energy and bandwidth efficiency, privacy protection, and context awareness (Zhou et al. 2019).”
From Deepfakes: current and future trends (2024) · cites this paper as Zhou et al. 2019
The cited source says what the claim attributes to it.
In the citing paper
“In the case of training a deep learning model in an edge computing environment, where distributed models are trained locally first and then updates are aggregated centrally (e.g., federated learning), the control of updates aggregation frequency has a significant influence on the communication overhead.”
From A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022) · cites this paper as [8]
In the citing paper
“Edge AI provides a promising solution for connected intelligence by enabling data collection, processing, transmission, and consumption at the network edge [29], [30].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [30]
In the citing paper
“All of these reviews only have a small fraction to discuss the edge DNN design which is the key element of edge intelligence systems.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [13]
In the citing paper
“Smart city [113] is another important application scenario for deep-learning-enabled edge computing.”
From Deep learning for edge computing applications: A State-of-the-Art survey (2020) · cites this paper as [113]
In the citing paper
“In the current scenario, Blockchain provides a high degree of privacy for health data [49].”
From 6G Communication Technology: A Vision on Intelligent Healthcare (2021) · cites this paper as [49]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Inference metrics are counted as five but six are listed
MinorThe section introduces five inference metrics, but its numbered list runs from latency through memory footprint and contains six.
“To describe the service quality of the EI model inference, we introduce the following five metrics.”
“## 6) Memory Footprint:”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 5×
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
BackgroundMethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 7×
“This is because for DNNs as exemplified by AlexNet, the energy of the convolutional layers dominates the total energy cost, while the number in the fully connected layers contributes most of the total number of weights in the DNN.”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 4×
“4, each neuron in LSTM is called memory cell and includes a multiplicative forget gate, input gate, and output gate.”
BackgroundInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 2×
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
MethodLearning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · cited 1×
“Leveraging the backpropagation mechanism [26], [27], the error rate is propagated back across the whole neural network, and the weights are updated based on the gradient and the learning rate.”
(2016) · Cited by 31,590
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 2×
“[32] V.”
Flagged first, then by citations
28 of the 168 references couldn’t be matched to a known paper.
Research works printed but not linked: 11
- 0, 3 AI Trends for Enterprise Computing
- 0, Microsoft Interactive Cloud Gaming
- 0, Democratizing AI
- hsieh, 2017, Gaia: Geo-distributed machine learning approaching LAN speeds, Proc NSDI, 629
- 2018, 5 Trends Emerge in the Gartner Hype Cycle for Emerging Technologies
- 0, Cisco global cloud index Forecast and methodology 2016–2021
- 0, Accelerating AI on the Intelligent Edge
- 2017, IEC White Paper Edge Intelligence
- 0, Edge Intelligence for Industrial Internet of Things
- han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 1135
- 2018, 5 Trends Emerge in the Gartner Hype Cycle for Emerging Technologies
Cited by
Sorted by citations
Items 1,701–1,800 of 2,413
Edge AI Online Training Architecture Using Multi-Phase-Quantization Optimizer
Akeno, I., Yamazaki, H., Asai, T., & Ando, K. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650299 · Cited by 1
Viewing Distance-Aware Volumetric Video Caching and Rendering for XR Services
Pei, Y., Li, M., Qu, K., et al. (2024) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc62479.2024.10681793 · Cited by 1
“To enhance the XR users’ quality-of-experience (QoE), mobile edge computing (MEC) technologies can be utilized by deploying storage and computing resources at access points (APs) near the XR users [4].”
BackgroundPutra, P. D. (2024) · International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP) · doi:10.1109/ict-pep63827.2024.10733513 · Cited by 1
RoleML: a Role-Oriented Programming Model for Customizable Distributed Machine Learning on Edges
Tan, Y., Yang, L., Li, W., & Wu, Y. (2024) · International Middleware Conference · doi:10.1145/3652892.3700765 · Cited by 1
“With the emergence of edge computing, these issues can now be addressed by training models directly on edge devices and transmitting only parameters or gradients for aggregation [27, 47].”
Towards an Asset Performance Management Reference Framework for Distributed Industrial Machinery
Landmann, M., Künster, N., Louw, L., et al. (2024) · Procedia CIRP · doi:10.1016/j.procir.2024.10.289 · Cited by 1
Forest Fire Image Classification Through Decentralized DNN Inference
Papaioannou, D., Mygdalis, V., & Pitas, I. (2024) · IEEE International Conference on Image Processing Workshops (ICIPW) · doi:10.1109/icipcw64161.2024.10769107 · Cited by 1
“In deep learning problems, many current approaches re-volve around architectures operating within an edge-to-cloud DNN inference framework [4].”
From Theory to Practice: Implementing Meta-Learning in 6G Wireless Infrastructure
Zeshan, A., Ouameur, M. A., Alam, M. Z., & Le, T.-A. D. (2024) · Telecom · doi:10.3390/telecom5040063 · Cited by 1
Momentum-Based Contextual Federated Reinforcement Learning
Yue, S., Hua, X., Deng, Y., Chen, L.-L., Ren, J., & Zhang, Y. (2024) · IEEE Transactions on Networking · doi:10.1109/tnet.2024.3510352 · Cited by 1
“In recent years, a number of FRL approaches have been proposed to co-train policy models without violating the constraints of data confidentiality [25], [26], [27].”
FusedInf: Efficient Swapping of DNN Models for On-Demand Serverless Inference Services on the Edge
Taki, S. U., Padmanabhan, A., & Mastorakis, S. (2024) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec62691.2024.00016 · Cited by 1
“This trend necessitates a paradigm shift from traditional cloud-optimized DNN models to lightweight and resource-efficient models tailored for resource-constrained edge devices [12].”
Perspective Chapter: The Evolution of Edge Computing in the IoT Era of the 22nd Century
Nwokoma, F., & Akujuobi, C. M. (2024) · IntechOpen eBooks · doi:10.5772/intechopen.1006375 · Cited by 1
Cloud Computing: Innovations and Impacts on Global Data Infrastructure
Banumathi, S., Sivajothi, E., Indumathi.G., S., Kefyalew, E. Y., Sivakumar, J., & Priya, V. B. (2025) · International Conference on Computational, Communication and Information Technology (ICCCIT) · doi:10.1109/icccit62592.2025.10927743 · Cited by 2
Preprocessing and Framework for Edge Intelligence in Air Quality Control: Work on Progress
Prasetyo, A. P. P., Idris, M., Fakhrurroja, H., & Stiawan, D. (2024) · 2024 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) · doi:10.1109/icimcis63449.2024.10957284 · Cited by 2
“This framework should encompass the key architectural components, the enabling technologies, and the specific applications that can benefit from this paradigm shift [26] [10].”
InfluentialLiu, L., Zhang, F., Cheng, Y., Tang, G., Yan, J., & Lai, P. (2025) · Structural Health Monitoring · doi:10.1177/14759217251329165 · Cited by 1
“21 EIA supports deploying DLM directly to the edge devices that generate data to achieve real-time computation, thereby greatly reducing inference latency and has received extensive attention from researchers.”
Optimized Cooperative Inference for Energy-Efficient and Low-Latency Mobile Edge Computing
Choi, H.-H., & Lee, K. (2025) · International Conference on Information Networking · doi:10.1109/icoin63865.2025.10993081 · Cited by 1
“Previous studies have focused on system architecture, algorithms, and evaluations [3]–[6], but have overlooked the optimization of confidence thresholds, a key parameter affecting inference performance.”
Parvatha, N. (2022) · International Journal of Scientific Research and Management (IJSRM) · doi:10.18535/ijsrm/v10i11.ec02 · Cited by 1
Interaction-Aware Resource Reservation for Edge-Assisted Mobile Extended Reality
Pei, Y., Hu, S., Zhou, C., et al. (2025) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc65529.2025.11149304 · Cited by 1
“To address this limitation, XR devices can leverage mobile edge computing by offloading complex rendering tasks to nearby edge servers [4].”
TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
Liu, W., Zhan, Z., Joe‐Wong, C., et al. (2025) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs63083.2025.00102 · Cited by 1
“With the exponential growth in data generation from geographically distributed locations and the proliferation of edge computing technologies [1], federated learning (FL) [2]–[5] has gained much attention as it enables distributed model training through multiple collaborative edge devices without…”
Self-citationTang, Y., Zhang, T., Zhu, K., & Ren, F. (2025) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc67675.2025.00059 · Cited by 2
“In response to these challenges, edge computing with deep learning, also named edge intelligence (EI), has emerged as a promising solution [2].”
Fake News Detection Using Explainable Artificial Intelligence
Singh, S. K., Assi, S. A., Ginige, T., Mohammed, A. H., B.Wahit, F., & Obe, D. A.-J. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-96-7749-8_31 · Cited by 2
Distributed Cognition with Edge Architecture Enabling Intelligent Machines
Patias, I. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-1357-4_13 · Cited by 1
A Proximal Iteratively Reweighted Approach for Efficient Network Sparsification
Wang, H., Yang, X., Shi, Y., & Lin, J. (2020) · IEEE Transactions on Computers · doi:10.1109/tc.2020.3044142 · Cited by 2
Image Search System Based on Feature Vectors of Convolutional Neural Network
Diana, M., Amagasaki, M., & Iida, M. (2020) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon50793.2020.9293773 · Cited by 1
“CNN has shown good performance in classification [8], [9].”
MethodBožanić, M., & Sinha, S. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-69273-5_8 · Cited by 1
Edge Analytics and Deep Learning for Sustainable Development
Singh, S. K., Chakraborty, S., & Soodan, V. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-70183-3_10 · Cited by 1
Approaching Optimal Nonlinear Dimensionality Reduction by a Spiking Neural Network
Anzueto-Ríos, Á., Gomez-Castaneda, F., Flores-Nava, L. M., et al. (2021) · Electronics · doi:10.3390/electronics10141679 · Cited by 1
“This type of framework is found in [19].”
BackgroundOnline Task Scheduling for DNN-Based Applications over Cloud, Edge and End Devices
Zhong, L., Shi, J., Shi, L., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86137-7_20 · Cited by 1
SECCEG: A Secure and Efficient Cryptographic Co-processor Based on Embedded GPU System
Guang, F., Zheng, F., Dong, J., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86130-8_9 · Cited by 1
Shi, Y., Yang, K., Yang, Z., et al. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-823817-2.00010-3 · Cited by 1
An Empirical Study of Inter-cluster Resource Orchestration within Federated Cloud Clusters
Lindsay, D., Yeung, G., Elkhatib, Y., et al. (2021) · IEEE International Conference on Joint Cloud Computing (JCC) · doi:10.1109/jcc53141.2021.00019 · Cited by 1
“This is particularly important with the growing prominence of training and inference at the edge [33], where even an additional fraction of a second could be detrimental to sensitive ML-driven applications in security, self-driving vehicles, and traffic management [22].”
BackgroundOptimal Task Assignment for Integrated Cloud and Edge Networks With Tree Topology
Guan, X., Ji, T., Wan, X., et al. (2021) · IEEE Communications Letters · doi:10.1109/lcomm.2021.3103011 · Cited by 1
Intelligent Link Management for Vehicular Internet Access
Xu, W., Zhou, H., & Shen, X. (2021) · Springer eBooks · doi:10.1007/978-3-030-88991-3_4 · Cited by 1
Intelligent Networking enabled Vehicular Distributed Learning
Xu, W., Zhou, H., & Shen, X. (2021) · Springer eBooks · doi:10.1007/978-3-030-88991-3_5 · Cited by 1
Looking at the Digitized World from Different Perspectives
Za, S., Consorti, A., & Virili, F. (2021) · Lecture notes in information systems and organisation · doi:10.1007/978-3-030-86858-1_18 · Cited by 1
WASP: A Wearable Super-Computing Platform for Distributed Intelligence in Multi-Agent Systems
Patnayak, C., McClure, J. E., & Williams, R. K. (2021) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec49654.2021.9622784 · Cited by 1
Heterogeneous platform-aware workload feature recognition for edge intelligence
Li, D., Li, Y., Hu, H., Zhang, T., & Jiang, C. (2022) · Physical Communication · doi:10.1016/j.phycom.2022.101620 · Cited by 1
Diversity Learning: Introducing the Space-time Scheme to Ensemble Learning
Zhu, Z., Fan, P., & Letaief, K. B. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771824 · Cited by 1
“Additionally, in recent years, distributed learning has been applied in some promising scenarios such as edge intelligence computing [10] and federated learning [11].”
BackgroundFlexible Parallel Learning in Edge Scenarios: Communication, Computational and Energy Cost
Malandrino, F., & Chiasserini, C. F. (2022) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops53856.2022.9767275 · Cited by 2
Tharwat, M. E. A. A., Fudzee, M. F. M., Kasim, S. B., et al. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-00828-3_6 · Cited by 1
Inference Acceleration with Adaptive Distributed DNN Partition over Dynamic Video Stream
Cao, J., Li, B., Fan, M., & Liu, H. (2022) · Algorithms · doi:10.3390/a15070244 · Cited by 1
MSSA-FL: High-Performance Multi-stage Semi-asynchronous Federated Learning with Non-IID Data
Wei, X., Hou, M., Ren, C., Li, X., & Yue, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10986-7_14 · Cited by 2
Overview of Edge Intelligence and Blockchain
Wang, X., Qiu, C., Ren, X., Xiong, Z., Leung, V. C. M., & Niyato, D. T. (2022) · Wireless networks · doi:10.1007/978-3-031-10186-1_2 · Cited by 1
Motivations for Integrating Edge Intelligence with Blockchain
Wang, X., Qiu, C., Ren, X., et al. (2022) · Wireless networks · doi:10.1007/978-3-031-10186-1_3 · Cited by 1
Electric Power Asynchronous Heterogeneous Data Accelerated Compression for Edge Computing
Wang, H., Rao, H., Gong, X., et al. (2022) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud55982.2022.00025 · Cited by 1
“There are three ways of collaboration, cloud-oriented edge-cloud collaboration and edge-oriented edge-cloud collaboration [31].”
BackgroundSelf-citationStegEdge: Privacy protection of unknown sensitive attributes in edge intelligence via deception
Zhang, J., Zhang, W., & Xu, J. (2022) · Journal of Computer Security · doi:10.3233/jcs-220042 · Cited by 1
“Consequently, the paradigm of edge intelligence has been recognized by researchers as a viable means of empowering user devices with the capabilities of AI [26, 49].”
Self-citationCNN Based Animal Repelling Device for Crop Protection
Amarendra, C., & Reddy, T. R. (2023) · Advances in transdisciplinary engineering · doi:10.3233/atde221256
Multi-Slot Dynamic Computing Resource Optimization in Edge Computing
Chen, P., Xu, H., Fan, X., et al. (2022) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp55476.2022.10039042 · Cited by 1
“Despite the advantages of edge computing, several challenges remain to be addressed [3].”
BackgroundAdaptive Progressive Image Enhancement for Edge-Assisted Mobile Vision
Feng, D., Zeng, L., Pu, L., et al. (2022) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn57253.2022.00121 · Cited by 1
“To mitigate these issues simultaneously, in this paper, we leverage the emerging edge intelligence paradigm [5] and present Apie (Adaptive progressive image enhancement), an edge-assisted image enhancement system for image delivery scenarios in mobile vision.”
MethodSelf-citationImpact of Digital Technologies on the Industrial Complex Development: The Russian Experience
SMIRNOVA, O. P., & Chesnyukova, L. K. (2023) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-30351-7_4 · Cited by 1
Joint Task Offloading and Resource Allocation Based on Transaction Mechanism
Wang, W., Wang, C., & Wang, W. (2023) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb58369.2023.10211322 · Cited by 1
“Compared with traditional cloud computing, edge computing can effectively reduce the execution time of tasks and reduce the transmission bandwidth of data in the network [5].”
BackgroundWu, Q., Wu, M., Chen, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03971 · Cited by 1
Self-citationDong, Y., Zhao, P. F., Yu, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.02177 · Cited by 1
“Recently, the emerging paradigm of collaborative Edge Intelligence (EI) rapidly draws significant interests from both academia [Zhou et al., 2019; Chen and Ran, 2019] and industry[Google, 2018; Microsoft, 2019], where the deployment of various Artificial Intelligence (AI) applications is pushed…”
InfluentialProactive Tasks Management based on a Deep Learning ModelPreprint
Kolomvatsos, K., & Anagnotopoulos, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12857 · Cited by 1
“The target is to minimize the trade off between the performance when executing tasks and meeting the constraints of nodes (e.g., energy resources [49]).”
BackgroundLearning Centric Power Allocation for Edge IntelligencePreprint
Wang, S., Wang, R., Hao, Q., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.11399 · Cited by 1
“To address this challenge brought by MTC, a promising solution is the edge intelligence technique [3]–[7] that uses an intelligent edge to collect data generated from MTC devices and trains a machine learning model or fine-tunes a pre-trained model at the edge.”
BackgroundSEEC: Semantic Vector Federation across Edge Computing EnvironmentsPreprint
Witherspoon, S., Steuer, D., Bent, G. A., & Desai, N. V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.13298 · Cited by 1
“The factors driving such a paradigm shift are fundamental: (a) costs involved in transporting large amounts of data to Cloud, (b) regulatory constraints in moving data across sites, and (c) latency in placing all data analytics in Cloud.”
BackgroundInfluentialYu, S., Chen, X., Zhou, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.10601 · Cited by 1
“Take the task of deep neural network (DNN) model partition [33] with sequential dependency as an example.”
MethodSelf-citationWang, R., & Yuan, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04407 · Cited by 1
“Mobile edge computing [185]–[188] and fog radio access network [189]–[192] have been considered as key techniques in future cellular communications.”
BackgroundAdaptive In-network Collaborative Caching for Enhanced Ensemble Deep Learning at EdgePreprint
Qin, Y., Wu, D., Xu, Z., Tian, J., & Zhang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12899 · Cited by 1
“It is the ensemble learning [2, 3] that provide a feasible way to handle the variance of a single neural network model.”
BackgroundLearning Centric Wireless Resource Allocation for Edge Computing: Algorithm and ExperimentPreprint
Zhou, L., Hong, Y., Wang, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.15371 · Cited by 1
“With the edge computing platform, various machine learning applications can reside at the edge, giving rise to an emerging paradigm termed edge intelligence [3].”
BackgroundDeep Learning Towards Edge Computing: Neural Networks Straight from Compressed Data.Preprint
dos Santos, S. F., & Almeida, J. (2020) · arXiv (Cornell University) · Cited by 1
Noise Is Useful: Exploiting Data Diversity for Edge IntelligencePreprint
Zeng, Z., Liu, Y., Tang, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05465 · Cited by 1
EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of VehiclesPreprint
Yu, S., Gong, X., Shi, Q., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.06056 · Cited by 1
“Edge computing [2] is a state-of-the-art computing paradigm by moving the cloud computing services and resources closer to end users, in order to achieve high data rates, saved bandwidth resources and improved the quality of service (QoS) for real-time services.”
BackgroundMethodInfluentialSelf-citationAccelerating Edge Intelligence via Integrated Sensing and CommunicationPreprint
Zhang, T., Wang, S., Li, G., Liu, F., Zhu, G., & Wang, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.09574 · Cited by 1
“Edge intelligence emerges as a promising solution to leverage massive data distributed at the network edge for training various machine learning models at the edge server [1]–[3].”
BackgroundAdvanced Manufacturing Cloud of Things (AMCoT) Framework
Hung, M., Chen, C., & Lin, Y. (2021) · doi:10.1002/9781119739920.ch7 · Cited by 1
(2022) · Wiley eBooks · doi:10.1002/9781119879893.refs · Cited by 1
Edge Computing in the Internet of Things: A SurveyPreprint
Elmassik, Z. (2023) · doi:10.36227/techrxiv.22121660.v1 · Cited by 1
Borsci, S., Lehtola, V., Nex, F., Yang, M. Y., Augustijn, E.-W., Bagheriye, L., Brüne, C., Kounadi, O., Li, J. J., Moreira, J., et al. (2023) · doi:10.32920/23808690.v1 · Cited by 1
Li, X., Sun, S., Liu, M., Ren, J., Jiang, X., & He, T. (2023) · doi:10.36227/techrxiv.24165687 · Cited by 2
Harnessing the Synergy: Federated Learning Meets Edge Computing in 5G EcosystemsPreprint
Ekellem, E. A. F. (2024) · doi:10.36227/techrxiv.170593908.89365140/v1 · Cited by 1
Yang, R., Li, Z., Yao, J., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-3930064/v1 · Cited by 1
Publish/Subscribe for Edge Intelligence: Systematic Review and Future ProspectsPreprint
Saleh, A., Tarkoma, S., Pirttikangas, S., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4872730 · Cited by 1
Edge-Constrained Video Analytics: A Comprehensive Survey on Detection, Tracking, and Recognition
Toshpulatov, M. A., Lee, W., & Cho, J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6614394
Sparse Optimization for Green Edge AI InferencePreprint
Yang, X., Hua, S., Shi, Y., Wang, H., Zhang, J., & Letaief, K. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10080
“For the edge AI inference system, energy efficiency is a key performance indicator [14], which motives us to focus on the energyefficient edge inference design.”
BackgroundSelf-citationCrowd-MECS: A Novel Crowdsourcing Framework for Mobile Edge Caching and SharingPreprint
Jiang, C., Gao, L. X., Wang, T., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04481
An Edge Computing-based Photo Crowdsourcing Framework for Real-time 3D ReconstructionPreprint
Yu, S., Chen, X., Wang, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01562
“To this end, multi-access edge computing (MEC) [8], [9], [10], has been proposed by the European Telecommunications Standards Institute (ETSI), which is viewed as an ideal solution to address the above challenges.”
Self-citationTraffic control for energy harvesting virtual small cells via reinforcement learning
Temesgene, D. A. (2020) · doi:10.5821/dissertation-2117-328205
“, to the edge, has given rise to an edge intelligence paradigm [137].”
BackgroundZeng, L., Chen, X., Zhou, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03257
“To tackle these challenges, a promising approach is to exploit available computation resources in the proximity to the data source with the emerging edge intelligence paradigm [13].”
BackgroundSelf-citationDynamic DNN Decomposition for Lossless Synergistic InferencePreprint
Zhang, B., Tian, X., Zhang, H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05952
“Besides, prior works require re-partitioning the whole DNN to accommodate dynamics of computation resources and network bandwidth [12].”
MethodDedeoğlu, M., Lin, S., Zhang, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09225
“To exemplify, a single barycenter WGAN model could represent the information in hundreds of cat image databases instead of storing the same information in hundreds of WGAN models with minimum accuracy loss at the edge server.”
MethodSelf-citationZhang, W. (2020) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss49785.2020.9316091
“Only by obtaining this informat ion synchronously can make full use of each piece of energy consumption data for big data analysis and sum up the laws of energy use [7-9].”
BackgroundReconfigurable Intelligent Surface Assisted Edge Machine LearningPreprint
Huang, S., Wang, S., Wang, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.03185
“Mobile edge computing (MEC) is naturally well-suited for the AIoriented networks, and the marriage of mobile edge computing (MEC) and AI has given rise to a new research area, called “edge intelligence (EI)” or “edge AI” [1]–[4].”
BackgroundClient-Based Intelligence for Resource Efficient Vehicular Big Data Transfer in Future 6G NetworkPreprint
Sliwa, B., Adam, R., & Wietfeld, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08624
“According to the classification scheme for edge intelligence provided by [54], the proposed data transfer method represents a level 3: on-device inference edge intelligence implementation where the model is trained in the cloud/offline and inference is run completely locally.”
BackgroundMethodTchaye-Kondi, J., Zhai, Y., & Zhu, L. (2021) · doi:10.36227/techrxiv.13698883.v2
“As shown in Fig.2a, the AE takes advantage of DNN splitting[26] property and splits the network architecture into two parts: Encoder and Decoder.”
MethodCreating Robust Deep Neural Networks With Coded Distributed Computing for IoT SystemsPreprint
Hadidi, R., Cao, J., & Kim, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.04447
“Processing the IoT data locally in-the-edge and on each individual device may suffer from poor performance and energy efficiency [7, 9].”
BackgroundGautam, R., MayankRaj, Kumar, A., et al. (2021) · International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) · doi:10.1109/icac3n53548.2021.9725726
“LITERATURE REVIEW According to the various papers present in other’s work, there are certain studies that keep an eye on trend insights and predicting for the Indian portion[15][16].”
BackgroundIntegrated 3C in NOMA-enabled Remote-E-Health SystemsPreprint
Liu, X., Liu, Y., Yang, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.09749
“To fulfill these requirements, EI is proposed to push network functions from the network centre to the network edge [8].”
BackgroundEnabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-designPreprint
Hao, C., Dotzel, J., Xiong, J., Luca Benini, C., Zhang, Z., & Chen, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.15750
Leveraging the Potentials of Federated AI Ecosystems
Röder, M., Kowalczyk, P., & Thiesse, F. (2021) · Lecture notes in information systems and organisation · doi:10.1007/978-3-030-86800-0_5
“Here it should be emphasized that private data are treated confidentially in the sense that they are not forwarded but rather remain with the data owner [12, 14].”
BackgroundMethodInfluentialPCRec: A Private Coding Computation Scheme Based on Edge Computing for Recommendation System
Zhai, M., Gu, F., Wang, J., Li, L., Lu, K., & Wang, J. (2020) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00049
“Toaddress these problems, edge computing (EC) was proposed to migrate the computing tasks of the cloud server to the edge devices [10].”
BackgroundManagement of Resource at the Network Edge for Federated LearningPreprint
Trindade, S., Bittencourt, L. F., & da Fonseca, N. L. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03428 · Cited by 5
“After 2010, AI has experienced a big surge due to the advances in deep learning, a method that has achieved human-level accuracy in some areas [35].”
BackgroundInfluentialIntelligent Sensing Scheduling for Mobile Target Tracking Wireless Sensor NetworksPreprint
Zhou, L., Leng, S., Liu, Q., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.01885
“In addition, the limited energy of sensor nodes cannot assure consecutive target tracking when the mobile targets invade with high moving speed [6], [7].”
BackgroundIndustrial Vision Optimization Distributed Strategy based on Edge Intelligence Collaboration
Song, Y., Shen, Y. C., Ding, P., et al. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498693
Refusing the Burden of Computation: Edge Computing and Sustainable ICT
de Valk, M. (2021) · A Peer-Reviewed Journal About · doi:10.7146/aprja.v10i1.128184
Li, S., Wang, T., Yang, S., & Yuan, Y. (2021) · International Conference of Optical Imaging and Measurement (ICOIM) · doi:10.1109/icoim52180.2021.9524402
An Overview of Technology Trends Towards Smarter Cities
Loke, S. W., & Rakotonirainy, A. (2021) · Springer eBooks · doi:10.1007/978-3-030-82318-4_1
An adaptive DNN Partition Algorithm Greedy Algorithm (ADPA)
Zhanglei (2021) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess52187.2021.9522172
Cost-efficient and Skew-aware Data Scheduling for Incremental Learning in 5G NetworkPreprint
Pu, L., Yuan, X., Xu, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.00799
“There has been a growing interest in marrying ML with edge computing during the last five years (see the surveys [25], [26] as references).”
BackgroundDeep Reinforcement Learning for Autonomous Mobile Networks in Micro-grids
Miozzo, M., Piovesan, N., Temesgene, D. A., & Dini, P. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-77939-9_8
Community-Structured Decentralized Learning for Resilient EI
Kuttivelil, H. S., & Obraczka, K. (2021) · ResilientFL · doi:10.1145/3477114.3488764
“EI has been classified [39] based on the levels of device, edge, and cloud involve-”
Background
Metadata
- Authors
- Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J.
- Affiliations
- Sun Yat-sen University (CN)
- Arizona State University (US)
- Venue
- Proceedings of the IEEE
- Published
- 2019-08
- Volume
- 107
- Issue
- 8
- Pages
- 1738-1762
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2950865323
- Semantic Scholar
- 928cd808aba140ec298508df87c5579811ff2f41
- Cited by
- 2,455
- References
- 168
- Citations by year
- 2026: 455 · 2025: 352 · 2024: 332 · 2023: 363 · 2022: 370 · 2021: 341 · 2020: 215 · 2019: 26
- FWCI
- 130.23
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Basic Research Program of China (2017YFB1001703)
- National Natural Science Foundation of China (U1711265, 61802449)
- Program for Guangdong Introducing Innovative and Entrepreneurial Teams (2017ZT07X355)
- Guangdong Natural Science Funds (2018A030313032)
- Fundamental Research Funds for the Central Universities (17lgjc40)
- Army Research Office (W911NF-16-1-0448)
- Defense Threat Reduction Agency (HDTRA1-13-1-0029)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- edge AI, edge computing, edge computing architecture, deep learning training, deep learning inference, Internet of Things, mobile computing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
